First model version
Browse files- config.json +32 -0
- main.py +1 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +107 -0
- tokenizer.json +0 -0
- tokenizer_config.json +113 -0
- trainer_state.json +2287 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bowphs/PhilTa-v2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"gradient_checkpointing": false,
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"num_decoder_layers": 12,
|
| 21 |
+
"num_heads": 12,
|
| 22 |
+
"num_layers": 12,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.25.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 126103
|
| 32 |
+
}
|
main.py
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
import insubdir0; print('Worked')
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:900c8b180cf08b250119116133d0fe769fa9d5bd027c22db60423d7d44b4732f
|
| 3 |
+
size 3135555525
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abcf7f71d1444fe501bcbf7ad1de6db3e22f07937f1643b317821791cbf20f3a
|
| 3 |
+
size 1567791285
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac55ae1ed00f1c792e39c8ea4221bda782153ba0669aaa5db758bcad7858db6f
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc3acd47c1bdf37b1d515454f47bdc2195f4304444d4bbcfebfde1a449fa24a4
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"clean_up_tokenization_spaces": true,
|
| 105 |
+
"eos_token": "</s>",
|
| 106 |
+
"extra_ids": 100,
|
| 107 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 108 |
+
"name_or_path": "bowphs/PhilTa-v2",
|
| 109 |
+
"pad_token": "<pad>",
|
| 110 |
+
"special_tokens_map_file": "/home/students/riemenschneider/.cache/huggingface/hub/models--bowphs--PhilTa-v2/snapshots/379f535ce51f007b08d4d7291a52c88855d85d9f/special_tokens_map.json",
|
| 111 |
+
"tokenizer_class": "T5Tokenizer",
|
| 112 |
+
"unk_token": "<unk>"
|
| 113 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2287 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 93.2776,
|
| 3 |
+
"best_model_checkpoint": "models/lemmatization-seed-2-philta_finally/checkpoint-164868",
|
| 4 |
+
"epoch": 32.99984990243659,
|
| 5 |
+
"global_step": 164868,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 9.979983987189753e-05,
|
| 13 |
+
"loss": 2.1491,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.2,
|
| 18 |
+
"learning_rate": 9.959967974379504e-05,
|
| 19 |
+
"loss": 0.6907,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.3,
|
| 24 |
+
"learning_rate": 9.939951961569256e-05,
|
| 25 |
+
"loss": 0.5698,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.4,
|
| 30 |
+
"learning_rate": 9.919935948759008e-05,
|
| 31 |
+
"loss": 0.5212,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.5,
|
| 36 |
+
"learning_rate": 9.89991993594876e-05,
|
| 37 |
+
"loss": 0.4783,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.6,
|
| 42 |
+
"learning_rate": 9.879903923138511e-05,
|
| 43 |
+
"loss": 0.468,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.7,
|
| 48 |
+
"learning_rate": 9.859887910328262e-05,
|
| 49 |
+
"loss": 0.4402,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.8,
|
| 54 |
+
"learning_rate": 9.839871897518015e-05,
|
| 55 |
+
"loss": 0.4079,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.9,
|
| 60 |
+
"learning_rate": 9.819855884707767e-05,
|
| 61 |
+
"loss": 0.3856,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.0,
|
| 66 |
+
"eval_loss": 0.28772488236427307,
|
| 67 |
+
"eval_lowercase_match_acc": 88.1229,
|
| 68 |
+
"eval_runtime": 4369.0377,
|
| 69 |
+
"eval_samples_per_second": 5.066,
|
| 70 |
+
"eval_steps_per_second": 2.533,
|
| 71 |
+
"step": 4996
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.0,
|
| 75 |
+
"learning_rate": 9.799839871897519e-05,
|
| 76 |
+
"loss": 0.3696,
|
| 77 |
+
"step": 5000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.1,
|
| 81 |
+
"learning_rate": 9.77982385908727e-05,
|
| 82 |
+
"loss": 0.3373,
|
| 83 |
+
"step": 5500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.2,
|
| 87 |
+
"learning_rate": 9.759807846277023e-05,
|
| 88 |
+
"loss": 0.3308,
|
| 89 |
+
"step": 6000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.3,
|
| 93 |
+
"learning_rate": 9.739791833466774e-05,
|
| 94 |
+
"loss": 0.3049,
|
| 95 |
+
"step": 6500
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.4,
|
| 99 |
+
"learning_rate": 9.719775820656527e-05,
|
| 100 |
+
"loss": 0.3195,
|
| 101 |
+
"step": 7000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.5,
|
| 105 |
+
"learning_rate": 9.699759807846276e-05,
|
| 106 |
+
"loss": 0.2952,
|
| 107 |
+
"step": 7500
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.6,
|
| 111 |
+
"learning_rate": 9.679743795036029e-05,
|
| 112 |
+
"loss": 0.2949,
|
| 113 |
+
"step": 8000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.7,
|
| 117 |
+
"learning_rate": 9.659727782225782e-05,
|
| 118 |
+
"loss": 0.2897,
|
| 119 |
+
"step": 8500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.8,
|
| 123 |
+
"learning_rate": 9.639711769415533e-05,
|
| 124 |
+
"loss": 0.2725,
|
| 125 |
+
"step": 9000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.9,
|
| 129 |
+
"learning_rate": 9.619695756605284e-05,
|
| 130 |
+
"loss": 0.2866,
|
| 131 |
+
"step": 9500
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 2.0,
|
| 135 |
+
"eval_loss": 0.23798207938671112,
|
| 136 |
+
"eval_lowercase_match_acc": 90.1242,
|
| 137 |
+
"eval_runtime": 5070.7184,
|
| 138 |
+
"eval_samples_per_second": 4.365,
|
| 139 |
+
"eval_steps_per_second": 2.183,
|
| 140 |
+
"step": 9992
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.0,
|
| 144 |
+
"learning_rate": 9.599679743795037e-05,
|
| 145 |
+
"loss": 0.2696,
|
| 146 |
+
"step": 10000
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.1,
|
| 150 |
+
"learning_rate": 9.579663730984788e-05,
|
| 151 |
+
"loss": 0.2399,
|
| 152 |
+
"step": 10500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.2,
|
| 156 |
+
"learning_rate": 9.559647718174541e-05,
|
| 157 |
+
"loss": 0.2305,
|
| 158 |
+
"step": 11000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.3,
|
| 162 |
+
"learning_rate": 9.539631705364291e-05,
|
| 163 |
+
"loss": 0.2285,
|
| 164 |
+
"step": 11500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.4,
|
| 168 |
+
"learning_rate": 9.519615692554043e-05,
|
| 169 |
+
"loss": 0.233,
|
| 170 |
+
"step": 12000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.5,
|
| 174 |
+
"learning_rate": 9.499599679743796e-05,
|
| 175 |
+
"loss": 0.2284,
|
| 176 |
+
"step": 12500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.6,
|
| 180 |
+
"learning_rate": 9.479583666933547e-05,
|
| 181 |
+
"loss": 0.2302,
|
| 182 |
+
"step": 13000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.7,
|
| 186 |
+
"learning_rate": 9.459567654123299e-05,
|
| 187 |
+
"loss": 0.2195,
|
| 188 |
+
"step": 13500
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.8,
|
| 192 |
+
"learning_rate": 9.439551641313051e-05,
|
| 193 |
+
"loss": 0.2267,
|
| 194 |
+
"step": 14000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.9,
|
| 198 |
+
"learning_rate": 9.419535628502803e-05,
|
| 199 |
+
"loss": 0.2181,
|
| 200 |
+
"step": 14500
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.0,
|
| 204 |
+
"eval_loss": 0.21965482831001282,
|
| 205 |
+
"eval_lowercase_match_acc": 91.1904,
|
| 206 |
+
"eval_runtime": 5163.2805,
|
| 207 |
+
"eval_samples_per_second": 4.287,
|
| 208 |
+
"eval_steps_per_second": 2.144,
|
| 209 |
+
"step": 14988
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 3.0,
|
| 213 |
+
"learning_rate": 9.399519615692555e-05,
|
| 214 |
+
"loss": 0.2145,
|
| 215 |
+
"step": 15000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 3.1,
|
| 219 |
+
"learning_rate": 9.379503602882305e-05,
|
| 220 |
+
"loss": 0.1931,
|
| 221 |
+
"step": 15500
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 3.2,
|
| 225 |
+
"learning_rate": 9.359487590072058e-05,
|
| 226 |
+
"loss": 0.1881,
|
| 227 |
+
"step": 16000
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 3.3,
|
| 231 |
+
"learning_rate": 9.33947157726181e-05,
|
| 232 |
+
"loss": 0.1895,
|
| 233 |
+
"step": 16500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.4,
|
| 237 |
+
"learning_rate": 9.319455564451562e-05,
|
| 238 |
+
"loss": 0.1819,
|
| 239 |
+
"step": 17000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.5,
|
| 243 |
+
"learning_rate": 9.299439551641313e-05,
|
| 244 |
+
"loss": 0.182,
|
| 245 |
+
"step": 17500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.6,
|
| 249 |
+
"learning_rate": 9.279423538831066e-05,
|
| 250 |
+
"loss": 0.1837,
|
| 251 |
+
"step": 18000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.7,
|
| 255 |
+
"learning_rate": 9.259407526020817e-05,
|
| 256 |
+
"loss": 0.1839,
|
| 257 |
+
"step": 18500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.8,
|
| 261 |
+
"learning_rate": 9.23939151321057e-05,
|
| 262 |
+
"loss": 0.1757,
|
| 263 |
+
"step": 19000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.9,
|
| 267 |
+
"learning_rate": 9.219375500400321e-05,
|
| 268 |
+
"loss": 0.178,
|
| 269 |
+
"step": 19500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 4.0,
|
| 273 |
+
"eval_loss": 0.2106914520263672,
|
| 274 |
+
"eval_lowercase_match_acc": 91.7326,
|
| 275 |
+
"eval_runtime": 3762.7729,
|
| 276 |
+
"eval_samples_per_second": 5.883,
|
| 277 |
+
"eval_steps_per_second": 2.941,
|
| 278 |
+
"step": 19984
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 4.0,
|
| 282 |
+
"learning_rate": 9.199359487590072e-05,
|
| 283 |
+
"loss": 0.1833,
|
| 284 |
+
"step": 20000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.1,
|
| 288 |
+
"learning_rate": 9.179343474779825e-05,
|
| 289 |
+
"loss": 0.1575,
|
| 290 |
+
"step": 20500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.2,
|
| 294 |
+
"learning_rate": 9.159327461969576e-05,
|
| 295 |
+
"loss": 0.1572,
|
| 296 |
+
"step": 21000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.3,
|
| 300 |
+
"learning_rate": 9.139311449159327e-05,
|
| 301 |
+
"loss": 0.159,
|
| 302 |
+
"step": 21500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 4.4,
|
| 306 |
+
"learning_rate": 9.11929543634908e-05,
|
| 307 |
+
"loss": 0.1535,
|
| 308 |
+
"step": 22000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.5,
|
| 312 |
+
"learning_rate": 9.099279423538831e-05,
|
| 313 |
+
"loss": 0.1612,
|
| 314 |
+
"step": 22500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.6,
|
| 318 |
+
"learning_rate": 9.079263410728584e-05,
|
| 319 |
+
"loss": 0.1524,
|
| 320 |
+
"step": 23000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 4.7,
|
| 324 |
+
"learning_rate": 9.059247397918335e-05,
|
| 325 |
+
"loss": 0.1611,
|
| 326 |
+
"step": 23500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.8,
|
| 330 |
+
"learning_rate": 9.039231385108086e-05,
|
| 331 |
+
"loss": 0.1533,
|
| 332 |
+
"step": 24000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.9,
|
| 336 |
+
"learning_rate": 9.019215372297839e-05,
|
| 337 |
+
"loss": 0.1537,
|
| 338 |
+
"step": 24500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 5.0,
|
| 342 |
+
"eval_loss": 0.20324945449829102,
|
| 343 |
+
"eval_lowercase_match_acc": 92.0352,
|
| 344 |
+
"eval_runtime": 3885.1477,
|
| 345 |
+
"eval_samples_per_second": 5.697,
|
| 346 |
+
"eval_steps_per_second": 2.849,
|
| 347 |
+
"step": 24980
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 5.0,
|
| 351 |
+
"learning_rate": 8.99919935948759e-05,
|
| 352 |
+
"loss": 0.1492,
|
| 353 |
+
"step": 25000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 5.1,
|
| 357 |
+
"learning_rate": 8.979183346677342e-05,
|
| 358 |
+
"loss": 0.1344,
|
| 359 |
+
"step": 25500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 5.2,
|
| 363 |
+
"learning_rate": 8.959167333867094e-05,
|
| 364 |
+
"loss": 0.1317,
|
| 365 |
+
"step": 26000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 5.3,
|
| 369 |
+
"learning_rate": 8.939151321056846e-05,
|
| 370 |
+
"loss": 0.1319,
|
| 371 |
+
"step": 26500
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 5.4,
|
| 375 |
+
"learning_rate": 8.919135308246598e-05,
|
| 376 |
+
"loss": 0.1314,
|
| 377 |
+
"step": 27000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 5.5,
|
| 381 |
+
"learning_rate": 8.89911929543635e-05,
|
| 382 |
+
"loss": 0.1361,
|
| 383 |
+
"step": 27500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 5.6,
|
| 387 |
+
"learning_rate": 8.879103282626101e-05,
|
| 388 |
+
"loss": 0.1348,
|
| 389 |
+
"step": 28000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 5.7,
|
| 393 |
+
"learning_rate": 8.859087269815853e-05,
|
| 394 |
+
"loss": 0.127,
|
| 395 |
+
"step": 28500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 5.8,
|
| 399 |
+
"learning_rate": 8.839071257005605e-05,
|
| 400 |
+
"loss": 0.137,
|
| 401 |
+
"step": 29000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 5.9,
|
| 405 |
+
"learning_rate": 8.819055244195357e-05,
|
| 406 |
+
"loss": 0.1358,
|
| 407 |
+
"step": 29500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 6.0,
|
| 411 |
+
"eval_loss": 0.2009614259004593,
|
| 412 |
+
"eval_lowercase_match_acc": 92.1572,
|
| 413 |
+
"eval_runtime": 4606.4788,
|
| 414 |
+
"eval_samples_per_second": 4.805,
|
| 415 |
+
"eval_steps_per_second": 2.403,
|
| 416 |
+
"step": 29976
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 6.0,
|
| 420 |
+
"learning_rate": 8.799039231385109e-05,
|
| 421 |
+
"loss": 0.1308,
|
| 422 |
+
"step": 30000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 6.1,
|
| 426 |
+
"learning_rate": 8.77902321857486e-05,
|
| 427 |
+
"loss": 0.113,
|
| 428 |
+
"step": 30500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 6.2,
|
| 432 |
+
"learning_rate": 8.759007205764613e-05,
|
| 433 |
+
"loss": 0.1144,
|
| 434 |
+
"step": 31000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 6.3,
|
| 438 |
+
"learning_rate": 8.738991192954364e-05,
|
| 439 |
+
"loss": 0.1135,
|
| 440 |
+
"step": 31500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 6.41,
|
| 444 |
+
"learning_rate": 8.718975180144115e-05,
|
| 445 |
+
"loss": 0.1161,
|
| 446 |
+
"step": 32000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 6.51,
|
| 450 |
+
"learning_rate": 8.698959167333868e-05,
|
| 451 |
+
"loss": 0.1183,
|
| 452 |
+
"step": 32500
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 6.61,
|
| 456 |
+
"learning_rate": 8.678943154523619e-05,
|
| 457 |
+
"loss": 0.1162,
|
| 458 |
+
"step": 33000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 6.71,
|
| 462 |
+
"learning_rate": 8.658927141713372e-05,
|
| 463 |
+
"loss": 0.1124,
|
| 464 |
+
"step": 33500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 6.81,
|
| 468 |
+
"learning_rate": 8.638911128903123e-05,
|
| 469 |
+
"loss": 0.1106,
|
| 470 |
+
"step": 34000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 6.91,
|
| 474 |
+
"learning_rate": 8.618895116092874e-05,
|
| 475 |
+
"loss": 0.115,
|
| 476 |
+
"step": 34500
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 7.0,
|
| 480 |
+
"eval_loss": 0.20892679691314697,
|
| 481 |
+
"eval_lowercase_match_acc": 92.609,
|
| 482 |
+
"eval_runtime": 4588.1045,
|
| 483 |
+
"eval_samples_per_second": 4.824,
|
| 484 |
+
"eval_steps_per_second": 2.412,
|
| 485 |
+
"step": 34972
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 7.01,
|
| 489 |
+
"learning_rate": 8.598879103282627e-05,
|
| 490 |
+
"loss": 0.1188,
|
| 491 |
+
"step": 35000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 7.11,
|
| 495 |
+
"learning_rate": 8.578863090472378e-05,
|
| 496 |
+
"loss": 0.0967,
|
| 497 |
+
"step": 35500
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 7.21,
|
| 501 |
+
"learning_rate": 8.55884707766213e-05,
|
| 502 |
+
"loss": 0.1048,
|
| 503 |
+
"step": 36000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 7.31,
|
| 507 |
+
"learning_rate": 8.538831064851882e-05,
|
| 508 |
+
"loss": 0.0991,
|
| 509 |
+
"step": 36500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 7.41,
|
| 513 |
+
"learning_rate": 8.518815052041633e-05,
|
| 514 |
+
"loss": 0.096,
|
| 515 |
+
"step": 37000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 7.51,
|
| 519 |
+
"learning_rate": 8.498799039231386e-05,
|
| 520 |
+
"loss": 0.1028,
|
| 521 |
+
"step": 37500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 7.61,
|
| 525 |
+
"learning_rate": 8.478783026421137e-05,
|
| 526 |
+
"loss": 0.0968,
|
| 527 |
+
"step": 38000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 7.71,
|
| 531 |
+
"learning_rate": 8.458767013610889e-05,
|
| 532 |
+
"loss": 0.0999,
|
| 533 |
+
"step": 38500
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 7.81,
|
| 537 |
+
"learning_rate": 8.438751000800641e-05,
|
| 538 |
+
"loss": 0.0991,
|
| 539 |
+
"step": 39000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 7.91,
|
| 543 |
+
"learning_rate": 8.418734987990394e-05,
|
| 544 |
+
"loss": 0.0994,
|
| 545 |
+
"step": 39500
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 8.0,
|
| 549 |
+
"eval_loss": 0.2047615349292755,
|
| 550 |
+
"eval_lowercase_match_acc": 92.3921,
|
| 551 |
+
"eval_runtime": 4481.5661,
|
| 552 |
+
"eval_samples_per_second": 4.939,
|
| 553 |
+
"eval_steps_per_second": 2.47,
|
| 554 |
+
"step": 39968
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 8.01,
|
| 558 |
+
"learning_rate": 8.398718975180144e-05,
|
| 559 |
+
"loss": 0.1056,
|
| 560 |
+
"step": 40000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 8.11,
|
| 564 |
+
"learning_rate": 8.378702962369896e-05,
|
| 565 |
+
"loss": 0.0907,
|
| 566 |
+
"step": 40500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 8.21,
|
| 570 |
+
"learning_rate": 8.358686949559648e-05,
|
| 571 |
+
"loss": 0.0879,
|
| 572 |
+
"step": 41000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 8.31,
|
| 576 |
+
"learning_rate": 8.3386709367494e-05,
|
| 577 |
+
"loss": 0.0901,
|
| 578 |
+
"step": 41500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 8.41,
|
| 582 |
+
"learning_rate": 8.318654923939152e-05,
|
| 583 |
+
"loss": 0.0888,
|
| 584 |
+
"step": 42000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 8.51,
|
| 588 |
+
"learning_rate": 8.298638911128903e-05,
|
| 589 |
+
"loss": 0.0911,
|
| 590 |
+
"step": 42500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 8.61,
|
| 594 |
+
"learning_rate": 8.278622898318655e-05,
|
| 595 |
+
"loss": 0.0903,
|
| 596 |
+
"step": 43000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 8.71,
|
| 600 |
+
"learning_rate": 8.258606885508408e-05,
|
| 601 |
+
"loss": 0.0843,
|
| 602 |
+
"step": 43500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 8.81,
|
| 606 |
+
"learning_rate": 8.238590872698158e-05,
|
| 607 |
+
"loss": 0.0918,
|
| 608 |
+
"step": 44000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 8.91,
|
| 612 |
+
"learning_rate": 8.218574859887911e-05,
|
| 613 |
+
"loss": 0.0873,
|
| 614 |
+
"step": 44500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 9.0,
|
| 618 |
+
"eval_loss": 0.20837198197841644,
|
| 619 |
+
"eval_lowercase_match_acc": 92.8168,
|
| 620 |
+
"eval_runtime": 4924.2181,
|
| 621 |
+
"eval_samples_per_second": 4.495,
|
| 622 |
+
"eval_steps_per_second": 2.248,
|
| 623 |
+
"step": 44964
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 9.01,
|
| 627 |
+
"learning_rate": 8.198558847077662e-05,
|
| 628 |
+
"loss": 0.0907,
|
| 629 |
+
"step": 45000
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 9.11,
|
| 633 |
+
"learning_rate": 8.178542834267415e-05,
|
| 634 |
+
"loss": 0.0723,
|
| 635 |
+
"step": 45500
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 9.21,
|
| 639 |
+
"learning_rate": 8.158526821457166e-05,
|
| 640 |
+
"loss": 0.0744,
|
| 641 |
+
"step": 46000
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 9.31,
|
| 645 |
+
"learning_rate": 8.138510808646917e-05,
|
| 646 |
+
"loss": 0.0786,
|
| 647 |
+
"step": 46500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 9.41,
|
| 651 |
+
"learning_rate": 8.11849479583667e-05,
|
| 652 |
+
"loss": 0.0851,
|
| 653 |
+
"step": 47000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 9.51,
|
| 657 |
+
"learning_rate": 8.098478783026422e-05,
|
| 658 |
+
"loss": 0.0743,
|
| 659 |
+
"step": 47500
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 9.61,
|
| 663 |
+
"learning_rate": 8.078462770216172e-05,
|
| 664 |
+
"loss": 0.0826,
|
| 665 |
+
"step": 48000
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 9.71,
|
| 669 |
+
"learning_rate": 8.058446757405925e-05,
|
| 670 |
+
"loss": 0.0852,
|
| 671 |
+
"step": 48500
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 9.81,
|
| 675 |
+
"learning_rate": 8.038430744595678e-05,
|
| 676 |
+
"loss": 0.0789,
|
| 677 |
+
"step": 49000
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 9.91,
|
| 681 |
+
"learning_rate": 8.018414731785429e-05,
|
| 682 |
+
"loss": 0.0777,
|
| 683 |
+
"step": 49500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 10.0,
|
| 687 |
+
"eval_loss": 0.20926587283611298,
|
| 688 |
+
"eval_lowercase_match_acc": 92.8078,
|
| 689 |
+
"eval_runtime": 5857.6443,
|
| 690 |
+
"eval_samples_per_second": 3.779,
|
| 691 |
+
"eval_steps_per_second": 1.889,
|
| 692 |
+
"step": 49960
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 10.01,
|
| 696 |
+
"learning_rate": 7.99839871897518e-05,
|
| 697 |
+
"loss": 0.0772,
|
| 698 |
+
"step": 50000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 10.11,
|
| 702 |
+
"learning_rate": 7.978382706164931e-05,
|
| 703 |
+
"loss": 0.0687,
|
| 704 |
+
"step": 50500
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 10.21,
|
| 708 |
+
"learning_rate": 7.958366693354684e-05,
|
| 709 |
+
"loss": 0.0712,
|
| 710 |
+
"step": 51000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 10.31,
|
| 714 |
+
"learning_rate": 7.938350680544437e-05,
|
| 715 |
+
"loss": 0.071,
|
| 716 |
+
"step": 51500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 10.41,
|
| 720 |
+
"learning_rate": 7.918334667734188e-05,
|
| 721 |
+
"loss": 0.0706,
|
| 722 |
+
"step": 52000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 10.51,
|
| 726 |
+
"learning_rate": 7.89831865492394e-05,
|
| 727 |
+
"loss": 0.0713,
|
| 728 |
+
"step": 52500
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 10.61,
|
| 732 |
+
"learning_rate": 7.878302642113692e-05,
|
| 733 |
+
"loss": 0.0649,
|
| 734 |
+
"step": 53000
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 10.71,
|
| 738 |
+
"learning_rate": 7.858286629303443e-05,
|
| 739 |
+
"loss": 0.0747,
|
| 740 |
+
"step": 53500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 10.81,
|
| 744 |
+
"learning_rate": 7.838270616493195e-05,
|
| 745 |
+
"loss": 0.0692,
|
| 746 |
+
"step": 54000
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 10.91,
|
| 750 |
+
"learning_rate": 7.818254603682946e-05,
|
| 751 |
+
"loss": 0.0729,
|
| 752 |
+
"step": 54500
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 11.0,
|
| 756 |
+
"eval_loss": 0.2255134880542755,
|
| 757 |
+
"eval_lowercase_match_acc": 92.8529,
|
| 758 |
+
"eval_runtime": 4053.7342,
|
| 759 |
+
"eval_samples_per_second": 5.46,
|
| 760 |
+
"eval_steps_per_second": 2.73,
|
| 761 |
+
"step": 54956
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 11.01,
|
| 765 |
+
"learning_rate": 7.798238590872698e-05,
|
| 766 |
+
"loss": 0.0666,
|
| 767 |
+
"step": 55000
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 11.11,
|
| 771 |
+
"learning_rate": 7.778222578062451e-05,
|
| 772 |
+
"loss": 0.0544,
|
| 773 |
+
"step": 55500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 11.21,
|
| 777 |
+
"learning_rate": 7.758206565252202e-05,
|
| 778 |
+
"loss": 0.0667,
|
| 779 |
+
"step": 56000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 11.31,
|
| 783 |
+
"learning_rate": 7.738190552441954e-05,
|
| 784 |
+
"loss": 0.0623,
|
| 785 |
+
"step": 56500
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 11.41,
|
| 789 |
+
"learning_rate": 7.718174539631706e-05,
|
| 790 |
+
"loss": 0.06,
|
| 791 |
+
"step": 57000
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 11.51,
|
| 795 |
+
"learning_rate": 7.698158526821458e-05,
|
| 796 |
+
"loss": 0.068,
|
| 797 |
+
"step": 57500
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 11.61,
|
| 801 |
+
"learning_rate": 7.67814251401121e-05,
|
| 802 |
+
"loss": 0.0607,
|
| 803 |
+
"step": 58000
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 11.71,
|
| 807 |
+
"learning_rate": 7.65812650120096e-05,
|
| 808 |
+
"loss": 0.0614,
|
| 809 |
+
"step": 58500
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 11.81,
|
| 813 |
+
"learning_rate": 7.638110488390713e-05,
|
| 814 |
+
"loss": 0.066,
|
| 815 |
+
"step": 59000
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 11.91,
|
| 819 |
+
"learning_rate": 7.618094475580465e-05,
|
| 820 |
+
"loss": 0.0641,
|
| 821 |
+
"step": 59500
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 12.0,
|
| 825 |
+
"eval_loss": 0.2248515486717224,
|
| 826 |
+
"eval_lowercase_match_acc": 92.9388,
|
| 827 |
+
"eval_runtime": 5148.8388,
|
| 828 |
+
"eval_samples_per_second": 4.299,
|
| 829 |
+
"eval_steps_per_second": 2.15,
|
| 830 |
+
"step": 59952
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 12.01,
|
| 834 |
+
"learning_rate": 7.598078462770217e-05,
|
| 835 |
+
"loss": 0.0662,
|
| 836 |
+
"step": 60000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 12.11,
|
| 840 |
+
"learning_rate": 7.578062449959968e-05,
|
| 841 |
+
"loss": 0.0574,
|
| 842 |
+
"step": 60500
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 12.21,
|
| 846 |
+
"learning_rate": 7.55804643714972e-05,
|
| 847 |
+
"loss": 0.0529,
|
| 848 |
+
"step": 61000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 12.31,
|
| 852 |
+
"learning_rate": 7.538030424339472e-05,
|
| 853 |
+
"loss": 0.0578,
|
| 854 |
+
"step": 61500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 12.41,
|
| 858 |
+
"learning_rate": 7.518014411529225e-05,
|
| 859 |
+
"loss": 0.0538,
|
| 860 |
+
"step": 62000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 12.51,
|
| 864 |
+
"learning_rate": 7.497998398718974e-05,
|
| 865 |
+
"loss": 0.055,
|
| 866 |
+
"step": 62500
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 12.61,
|
| 870 |
+
"learning_rate": 7.477982385908727e-05,
|
| 871 |
+
"loss": 0.057,
|
| 872 |
+
"step": 63000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 12.71,
|
| 876 |
+
"learning_rate": 7.45796637309848e-05,
|
| 877 |
+
"loss": 0.056,
|
| 878 |
+
"step": 63500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 12.81,
|
| 882 |
+
"learning_rate": 7.437950360288231e-05,
|
| 883 |
+
"loss": 0.0564,
|
| 884 |
+
"step": 64000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 12.91,
|
| 888 |
+
"learning_rate": 7.417934347477982e-05,
|
| 889 |
+
"loss": 0.0617,
|
| 890 |
+
"step": 64500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 13.0,
|
| 894 |
+
"eval_loss": 0.23913247883319855,
|
| 895 |
+
"eval_lowercase_match_acc": 93.002,
|
| 896 |
+
"eval_runtime": 3464.1623,
|
| 897 |
+
"eval_samples_per_second": 6.39,
|
| 898 |
+
"eval_steps_per_second": 3.195,
|
| 899 |
+
"step": 64948
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 13.01,
|
| 903 |
+
"learning_rate": 7.397918334667735e-05,
|
| 904 |
+
"loss": 0.0568,
|
| 905 |
+
"step": 65000
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 13.11,
|
| 909 |
+
"learning_rate": 7.377902321857486e-05,
|
| 910 |
+
"loss": 0.0485,
|
| 911 |
+
"step": 65500
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 13.21,
|
| 915 |
+
"learning_rate": 7.357886309047239e-05,
|
| 916 |
+
"loss": 0.0473,
|
| 917 |
+
"step": 66000
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 13.31,
|
| 921 |
+
"learning_rate": 7.337870296236989e-05,
|
| 922 |
+
"loss": 0.048,
|
| 923 |
+
"step": 66500
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 13.41,
|
| 927 |
+
"learning_rate": 7.317854283426741e-05,
|
| 928 |
+
"loss": 0.0509,
|
| 929 |
+
"step": 67000
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 13.51,
|
| 933 |
+
"learning_rate": 7.297838270616494e-05,
|
| 934 |
+
"loss": 0.0527,
|
| 935 |
+
"step": 67500
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 13.61,
|
| 939 |
+
"learning_rate": 7.277822257806245e-05,
|
| 940 |
+
"loss": 0.051,
|
| 941 |
+
"step": 68000
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 13.71,
|
| 945 |
+
"learning_rate": 7.257806244995997e-05,
|
| 946 |
+
"loss": 0.0512,
|
| 947 |
+
"step": 68500
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 13.81,
|
| 951 |
+
"learning_rate": 7.237790232185749e-05,
|
| 952 |
+
"loss": 0.0512,
|
| 953 |
+
"step": 69000
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 13.91,
|
| 957 |
+
"learning_rate": 7.2177742193755e-05,
|
| 958 |
+
"loss": 0.0575,
|
| 959 |
+
"step": 69500
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 14.0,
|
| 963 |
+
"eval_loss": 0.25704246759414673,
|
| 964 |
+
"eval_lowercase_match_acc": 92.8168,
|
| 965 |
+
"eval_runtime": 4630.5226,
|
| 966 |
+
"eval_samples_per_second": 4.78,
|
| 967 |
+
"eval_steps_per_second": 2.39,
|
| 968 |
+
"step": 69944
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 14.01,
|
| 972 |
+
"learning_rate": 7.197758206565253e-05,
|
| 973 |
+
"loss": 0.0517,
|
| 974 |
+
"step": 70000
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 14.11,
|
| 978 |
+
"learning_rate": 7.177742193755004e-05,
|
| 979 |
+
"loss": 0.0408,
|
| 980 |
+
"step": 70500
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 14.21,
|
| 984 |
+
"learning_rate": 7.157726180944756e-05,
|
| 985 |
+
"loss": 0.0457,
|
| 986 |
+
"step": 71000
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 14.31,
|
| 990 |
+
"learning_rate": 7.137710168134508e-05,
|
| 991 |
+
"loss": 0.047,
|
| 992 |
+
"step": 71500
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 14.41,
|
| 996 |
+
"learning_rate": 7.11769415532426e-05,
|
| 997 |
+
"loss": 0.0452,
|
| 998 |
+
"step": 72000
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 14.51,
|
| 1002 |
+
"learning_rate": 7.097678142514011e-05,
|
| 1003 |
+
"loss": 0.0458,
|
| 1004 |
+
"step": 72500
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 14.61,
|
| 1008 |
+
"learning_rate": 7.077662129703764e-05,
|
| 1009 |
+
"loss": 0.0432,
|
| 1010 |
+
"step": 73000
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 14.71,
|
| 1014 |
+
"learning_rate": 7.057646116893515e-05,
|
| 1015 |
+
"loss": 0.0494,
|
| 1016 |
+
"step": 73500
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 14.81,
|
| 1020 |
+
"learning_rate": 7.037630104083268e-05,
|
| 1021 |
+
"loss": 0.0498,
|
| 1022 |
+
"step": 74000
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 14.91,
|
| 1026 |
+
"learning_rate": 7.017614091273019e-05,
|
| 1027 |
+
"loss": 0.0475,
|
| 1028 |
+
"step": 74500
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 15.0,
|
| 1032 |
+
"eval_loss": 0.2623473107814789,
|
| 1033 |
+
"eval_lowercase_match_acc": 93.0562,
|
| 1034 |
+
"eval_runtime": 5358.3874,
|
| 1035 |
+
"eval_samples_per_second": 4.131,
|
| 1036 |
+
"eval_steps_per_second": 2.066,
|
| 1037 |
+
"step": 74940
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 15.01,
|
| 1041 |
+
"learning_rate": 6.99759807846277e-05,
|
| 1042 |
+
"loss": 0.0486,
|
| 1043 |
+
"step": 75000
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 15.11,
|
| 1047 |
+
"learning_rate": 6.977582065652523e-05,
|
| 1048 |
+
"loss": 0.0389,
|
| 1049 |
+
"step": 75500
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 15.21,
|
| 1053 |
+
"learning_rate": 6.957566052842274e-05,
|
| 1054 |
+
"loss": 0.041,
|
| 1055 |
+
"step": 76000
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 15.31,
|
| 1059 |
+
"learning_rate": 6.937550040032025e-05,
|
| 1060 |
+
"loss": 0.0394,
|
| 1061 |
+
"step": 76500
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 15.41,
|
| 1065 |
+
"learning_rate": 6.917534027221778e-05,
|
| 1066 |
+
"loss": 0.0405,
|
| 1067 |
+
"step": 77000
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 15.51,
|
| 1071 |
+
"learning_rate": 6.897518014411529e-05,
|
| 1072 |
+
"loss": 0.0427,
|
| 1073 |
+
"step": 77500
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 15.61,
|
| 1077 |
+
"learning_rate": 6.877502001601282e-05,
|
| 1078 |
+
"loss": 0.0432,
|
| 1079 |
+
"step": 78000
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 15.71,
|
| 1083 |
+
"learning_rate": 6.857485988791033e-05,
|
| 1084 |
+
"loss": 0.042,
|
| 1085 |
+
"step": 78500
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 15.81,
|
| 1089 |
+
"learning_rate": 6.837469975980784e-05,
|
| 1090 |
+
"loss": 0.0417,
|
| 1091 |
+
"step": 79000
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 15.91,
|
| 1095 |
+
"learning_rate": 6.817453963170537e-05,
|
| 1096 |
+
"loss": 0.0435,
|
| 1097 |
+
"step": 79500
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 16.0,
|
| 1101 |
+
"eval_loss": 0.26566237211227417,
|
| 1102 |
+
"eval_lowercase_match_acc": 92.9885,
|
| 1103 |
+
"eval_runtime": 5585.7722,
|
| 1104 |
+
"eval_samples_per_second": 3.963,
|
| 1105 |
+
"eval_steps_per_second": 1.981,
|
| 1106 |
+
"step": 79936
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 16.01,
|
| 1110 |
+
"learning_rate": 6.797437950360288e-05,
|
| 1111 |
+
"loss": 0.044,
|
| 1112 |
+
"step": 80000
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 16.11,
|
| 1116 |
+
"learning_rate": 6.777421937550041e-05,
|
| 1117 |
+
"loss": 0.0354,
|
| 1118 |
+
"step": 80500
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 16.21,
|
| 1122 |
+
"learning_rate": 6.757405924739792e-05,
|
| 1123 |
+
"loss": 0.0392,
|
| 1124 |
+
"step": 81000
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 16.31,
|
| 1128 |
+
"learning_rate": 6.737389911929544e-05,
|
| 1129 |
+
"loss": 0.0379,
|
| 1130 |
+
"step": 81500
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 16.41,
|
| 1134 |
+
"learning_rate": 6.717373899119296e-05,
|
| 1135 |
+
"loss": 0.0406,
|
| 1136 |
+
"step": 82000
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 16.51,
|
| 1140 |
+
"learning_rate": 6.697357886309047e-05,
|
| 1141 |
+
"loss": 0.0393,
|
| 1142 |
+
"step": 82500
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 16.61,
|
| 1146 |
+
"learning_rate": 6.677341873498799e-05,
|
| 1147 |
+
"loss": 0.0381,
|
| 1148 |
+
"step": 83000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 16.71,
|
| 1152 |
+
"learning_rate": 6.657325860688551e-05,
|
| 1153 |
+
"loss": 0.0376,
|
| 1154 |
+
"step": 83500
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 16.81,
|
| 1158 |
+
"learning_rate": 6.637309847878303e-05,
|
| 1159 |
+
"loss": 0.0384,
|
| 1160 |
+
"step": 84000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 16.91,
|
| 1164 |
+
"learning_rate": 6.617293835068055e-05,
|
| 1165 |
+
"loss": 0.04,
|
| 1166 |
+
"step": 84500
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 17.0,
|
| 1170 |
+
"eval_loss": 0.27961936593055725,
|
| 1171 |
+
"eval_lowercase_match_acc": 93.0653,
|
| 1172 |
+
"eval_runtime": 5010.3314,
|
| 1173 |
+
"eval_samples_per_second": 4.418,
|
| 1174 |
+
"eval_steps_per_second": 2.209,
|
| 1175 |
+
"step": 84932
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 17.01,
|
| 1179 |
+
"learning_rate": 6.597277822257807e-05,
|
| 1180 |
+
"loss": 0.0363,
|
| 1181 |
+
"step": 85000
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 17.11,
|
| 1185 |
+
"learning_rate": 6.577261809447558e-05,
|
| 1186 |
+
"loss": 0.0302,
|
| 1187 |
+
"step": 85500
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 17.21,
|
| 1191 |
+
"learning_rate": 6.55724579663731e-05,
|
| 1192 |
+
"loss": 0.0361,
|
| 1193 |
+
"step": 86000
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 17.31,
|
| 1197 |
+
"learning_rate": 6.537229783827062e-05,
|
| 1198 |
+
"loss": 0.0325,
|
| 1199 |
+
"step": 86500
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 17.41,
|
| 1203 |
+
"learning_rate": 6.517213771016813e-05,
|
| 1204 |
+
"loss": 0.0356,
|
| 1205 |
+
"step": 87000
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 17.51,
|
| 1209 |
+
"learning_rate": 6.497197758206566e-05,
|
| 1210 |
+
"loss": 0.0339,
|
| 1211 |
+
"step": 87500
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 17.61,
|
| 1215 |
+
"learning_rate": 6.477181745396317e-05,
|
| 1216 |
+
"loss": 0.0357,
|
| 1217 |
+
"step": 88000
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 17.71,
|
| 1221 |
+
"learning_rate": 6.45716573258607e-05,
|
| 1222 |
+
"loss": 0.036,
|
| 1223 |
+
"step": 88500
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 17.81,
|
| 1227 |
+
"learning_rate": 6.437149719775821e-05,
|
| 1228 |
+
"loss": 0.0336,
|
| 1229 |
+
"step": 89000
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 17.91,
|
| 1233 |
+
"learning_rate": 6.417133706965572e-05,
|
| 1234 |
+
"loss": 0.0336,
|
| 1235 |
+
"step": 89500
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 18.0,
|
| 1239 |
+
"eval_loss": 0.2810537815093994,
|
| 1240 |
+
"eval_lowercase_match_acc": 93.0382,
|
| 1241 |
+
"eval_runtime": 3682.9518,
|
| 1242 |
+
"eval_samples_per_second": 6.01,
|
| 1243 |
+
"eval_steps_per_second": 3.005,
|
| 1244 |
+
"step": 89928
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 18.01,
|
| 1248 |
+
"learning_rate": 6.397117694155325e-05,
|
| 1249 |
+
"loss": 0.0336,
|
| 1250 |
+
"step": 90000
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 18.11,
|
| 1254 |
+
"learning_rate": 6.377101681345077e-05,
|
| 1255 |
+
"loss": 0.0291,
|
| 1256 |
+
"step": 90500
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 18.21,
|
| 1260 |
+
"learning_rate": 6.357085668534827e-05,
|
| 1261 |
+
"loss": 0.0293,
|
| 1262 |
+
"step": 91000
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 18.31,
|
| 1266 |
+
"learning_rate": 6.33706965572458e-05,
|
| 1267 |
+
"loss": 0.0293,
|
| 1268 |
+
"step": 91500
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 18.41,
|
| 1272 |
+
"learning_rate": 6.317053642914331e-05,
|
| 1273 |
+
"loss": 0.0324,
|
| 1274 |
+
"step": 92000
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 18.51,
|
| 1278 |
+
"learning_rate": 6.297037630104084e-05,
|
| 1279 |
+
"loss": 0.0331,
|
| 1280 |
+
"step": 92500
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 18.61,
|
| 1284 |
+
"learning_rate": 6.277021617293835e-05,
|
| 1285 |
+
"loss": 0.0334,
|
| 1286 |
+
"step": 93000
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 18.71,
|
| 1290 |
+
"learning_rate": 6.257005604483587e-05,
|
| 1291 |
+
"loss": 0.0309,
|
| 1292 |
+
"step": 93500
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 18.81,
|
| 1296 |
+
"learning_rate": 6.236989591673339e-05,
|
| 1297 |
+
"loss": 0.0329,
|
| 1298 |
+
"step": 94000
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 18.91,
|
| 1302 |
+
"learning_rate": 6.216973578863092e-05,
|
| 1303 |
+
"loss": 0.0329,
|
| 1304 |
+
"step": 94500
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 19.0,
|
| 1308 |
+
"eval_loss": 0.2951154112815857,
|
| 1309 |
+
"eval_lowercase_match_acc": 93.1421,
|
| 1310 |
+
"eval_runtime": 4374.9093,
|
| 1311 |
+
"eval_samples_per_second": 5.06,
|
| 1312 |
+
"eval_steps_per_second": 2.53,
|
| 1313 |
+
"step": 94924
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 19.02,
|
| 1317 |
+
"learning_rate": 6.196957566052842e-05,
|
| 1318 |
+
"loss": 0.0292,
|
| 1319 |
+
"step": 95000
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 19.12,
|
| 1323 |
+
"learning_rate": 6.176941553242594e-05,
|
| 1324 |
+
"loss": 0.0312,
|
| 1325 |
+
"step": 95500
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 19.22,
|
| 1329 |
+
"learning_rate": 6.156925540432347e-05,
|
| 1330 |
+
"loss": 0.0272,
|
| 1331 |
+
"step": 96000
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 19.32,
|
| 1335 |
+
"learning_rate": 6.136909527622098e-05,
|
| 1336 |
+
"loss": 0.0286,
|
| 1337 |
+
"step": 96500
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 19.42,
|
| 1341 |
+
"learning_rate": 6.11689351481185e-05,
|
| 1342 |
+
"loss": 0.0263,
|
| 1343 |
+
"step": 97000
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 19.52,
|
| 1347 |
+
"learning_rate": 6.096877502001601e-05,
|
| 1348 |
+
"loss": 0.0307,
|
| 1349 |
+
"step": 97500
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 19.62,
|
| 1353 |
+
"learning_rate": 6.0768614891913535e-05,
|
| 1354 |
+
"loss": 0.0282,
|
| 1355 |
+
"step": 98000
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 19.72,
|
| 1359 |
+
"learning_rate": 6.0568454763811054e-05,
|
| 1360 |
+
"loss": 0.0279,
|
| 1361 |
+
"step": 98500
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 19.82,
|
| 1365 |
+
"learning_rate": 6.036829463570857e-05,
|
| 1366 |
+
"loss": 0.0299,
|
| 1367 |
+
"step": 99000
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 19.92,
|
| 1371 |
+
"learning_rate": 6.016813450760609e-05,
|
| 1372 |
+
"loss": 0.0329,
|
| 1373 |
+
"step": 99500
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 20.0,
|
| 1377 |
+
"eval_loss": 0.3092300593852997,
|
| 1378 |
+
"eval_lowercase_match_acc": 93.1105,
|
| 1379 |
+
"eval_runtime": 4507.9299,
|
| 1380 |
+
"eval_samples_per_second": 4.91,
|
| 1381 |
+
"eval_steps_per_second": 2.455,
|
| 1382 |
+
"step": 99920
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 20.02,
|
| 1386 |
+
"learning_rate": 5.996797437950361e-05,
|
| 1387 |
+
"loss": 0.0273,
|
| 1388 |
+
"step": 100000
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 20.12,
|
| 1392 |
+
"learning_rate": 5.976781425140112e-05,
|
| 1393 |
+
"loss": 0.024,
|
| 1394 |
+
"step": 100500
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 20.22,
|
| 1398 |
+
"learning_rate": 5.9567654123298645e-05,
|
| 1399 |
+
"loss": 0.0258,
|
| 1400 |
+
"step": 101000
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 20.32,
|
| 1404 |
+
"learning_rate": 5.936749399519616e-05,
|
| 1405 |
+
"loss": 0.0269,
|
| 1406 |
+
"step": 101500
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 20.42,
|
| 1410 |
+
"learning_rate": 5.916733386709368e-05,
|
| 1411 |
+
"loss": 0.0278,
|
| 1412 |
+
"step": 102000
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 20.52,
|
| 1416 |
+
"learning_rate": 5.89671737389912e-05,
|
| 1417 |
+
"loss": 0.0236,
|
| 1418 |
+
"step": 102500
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 20.62,
|
| 1422 |
+
"learning_rate": 5.876701361088871e-05,
|
| 1423 |
+
"loss": 0.0244,
|
| 1424 |
+
"step": 103000
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 20.72,
|
| 1428 |
+
"learning_rate": 5.856685348278623e-05,
|
| 1429 |
+
"loss": 0.0269,
|
| 1430 |
+
"step": 103500
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 20.82,
|
| 1434 |
+
"learning_rate": 5.8366693354683756e-05,
|
| 1435 |
+
"loss": 0.0287,
|
| 1436 |
+
"step": 104000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 20.92,
|
| 1440 |
+
"learning_rate": 5.816653322658126e-05,
|
| 1441 |
+
"loss": 0.0283,
|
| 1442 |
+
"step": 104500
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 21.0,
|
| 1446 |
+
"eval_loss": 0.32634150981903076,
|
| 1447 |
+
"eval_lowercase_match_acc": 93.0382,
|
| 1448 |
+
"eval_runtime": 5218.5574,
|
| 1449 |
+
"eval_samples_per_second": 4.242,
|
| 1450 |
+
"eval_steps_per_second": 2.121,
|
| 1451 |
+
"step": 104916
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 21.02,
|
| 1455 |
+
"learning_rate": 5.796637309847879e-05,
|
| 1456 |
+
"loss": 0.0266,
|
| 1457 |
+
"step": 105000
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 21.12,
|
| 1461 |
+
"learning_rate": 5.77662129703763e-05,
|
| 1462 |
+
"loss": 0.0229,
|
| 1463 |
+
"step": 105500
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 21.22,
|
| 1467 |
+
"learning_rate": 5.756605284227382e-05,
|
| 1468 |
+
"loss": 0.0246,
|
| 1469 |
+
"step": 106000
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 21.32,
|
| 1473 |
+
"learning_rate": 5.736589271417134e-05,
|
| 1474 |
+
"loss": 0.0242,
|
| 1475 |
+
"step": 106500
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 21.42,
|
| 1479 |
+
"learning_rate": 5.7165732586068854e-05,
|
| 1480 |
+
"loss": 0.0257,
|
| 1481 |
+
"step": 107000
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 21.52,
|
| 1485 |
+
"learning_rate": 5.696557245796637e-05,
|
| 1486 |
+
"loss": 0.023,
|
| 1487 |
+
"step": 107500
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 21.62,
|
| 1491 |
+
"learning_rate": 5.67654123298639e-05,
|
| 1492 |
+
"loss": 0.0241,
|
| 1493 |
+
"step": 108000
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 21.72,
|
| 1497 |
+
"learning_rate": 5.656525220176141e-05,
|
| 1498 |
+
"loss": 0.0258,
|
| 1499 |
+
"step": 108500
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 21.82,
|
| 1503 |
+
"learning_rate": 5.636509207365893e-05,
|
| 1504 |
+
"loss": 0.0252,
|
| 1505 |
+
"step": 109000
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 21.92,
|
| 1509 |
+
"learning_rate": 5.6164931945556445e-05,
|
| 1510 |
+
"loss": 0.025,
|
| 1511 |
+
"step": 109500
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 22.0,
|
| 1515 |
+
"eval_loss": 0.33478838205337524,
|
| 1516 |
+
"eval_lowercase_match_acc": 93.1105,
|
| 1517 |
+
"eval_runtime": 4574.2489,
|
| 1518 |
+
"eval_samples_per_second": 4.839,
|
| 1519 |
+
"eval_steps_per_second": 2.42,
|
| 1520 |
+
"step": 109912
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 22.02,
|
| 1524 |
+
"learning_rate": 5.5964771817453964e-05,
|
| 1525 |
+
"loss": 0.026,
|
| 1526 |
+
"step": 110000
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 22.12,
|
| 1530 |
+
"learning_rate": 5.5764611689351484e-05,
|
| 1531 |
+
"loss": 0.0229,
|
| 1532 |
+
"step": 110500
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 22.22,
|
| 1536 |
+
"learning_rate": 5.5564451561249e-05,
|
| 1537 |
+
"loss": 0.0201,
|
| 1538 |
+
"step": 111000
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 22.32,
|
| 1542 |
+
"learning_rate": 5.536429143314652e-05,
|
| 1543 |
+
"loss": 0.0211,
|
| 1544 |
+
"step": 111500
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 22.42,
|
| 1548 |
+
"learning_rate": 5.516413130504404e-05,
|
| 1549 |
+
"loss": 0.0209,
|
| 1550 |
+
"step": 112000
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 22.52,
|
| 1554 |
+
"learning_rate": 5.4963971176941556e-05,
|
| 1555 |
+
"loss": 0.0197,
|
| 1556 |
+
"step": 112500
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 22.62,
|
| 1560 |
+
"learning_rate": 5.4763811048839075e-05,
|
| 1561 |
+
"loss": 0.0245,
|
| 1562 |
+
"step": 113000
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 22.72,
|
| 1566 |
+
"learning_rate": 5.456365092073659e-05,
|
| 1567 |
+
"loss": 0.0222,
|
| 1568 |
+
"step": 113500
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 22.82,
|
| 1572 |
+
"learning_rate": 5.436349079263411e-05,
|
| 1573 |
+
"loss": 0.0253,
|
| 1574 |
+
"step": 114000
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 22.92,
|
| 1578 |
+
"learning_rate": 5.4163330664531634e-05,
|
| 1579 |
+
"loss": 0.0202,
|
| 1580 |
+
"step": 114500
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 23.0,
|
| 1584 |
+
"eval_loss": 0.35109543800354004,
|
| 1585 |
+
"eval_lowercase_match_acc": 93.1873,
|
| 1586 |
+
"eval_runtime": 4159.2016,
|
| 1587 |
+
"eval_samples_per_second": 5.322,
|
| 1588 |
+
"eval_steps_per_second": 2.661,
|
| 1589 |
+
"step": 114908
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 23.02,
|
| 1593 |
+
"learning_rate": 5.396317053642914e-05,
|
| 1594 |
+
"loss": 0.0199,
|
| 1595 |
+
"step": 115000
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 23.12,
|
| 1599 |
+
"learning_rate": 5.3763010408326666e-05,
|
| 1600 |
+
"loss": 0.0173,
|
| 1601 |
+
"step": 115500
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 23.22,
|
| 1605 |
+
"learning_rate": 5.3562850280224186e-05,
|
| 1606 |
+
"loss": 0.0191,
|
| 1607 |
+
"step": 116000
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 23.32,
|
| 1611 |
+
"learning_rate": 5.33626901521217e-05,
|
| 1612 |
+
"loss": 0.0205,
|
| 1613 |
+
"step": 116500
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 23.42,
|
| 1617 |
+
"learning_rate": 5.316253002401922e-05,
|
| 1618 |
+
"loss": 0.0214,
|
| 1619 |
+
"step": 117000
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 23.52,
|
| 1623 |
+
"learning_rate": 5.296236989591674e-05,
|
| 1624 |
+
"loss": 0.0206,
|
| 1625 |
+
"step": 117500
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 23.62,
|
| 1629 |
+
"learning_rate": 5.276220976781425e-05,
|
| 1630 |
+
"loss": 0.0206,
|
| 1631 |
+
"step": 118000
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 23.72,
|
| 1635 |
+
"learning_rate": 5.256204963971178e-05,
|
| 1636 |
+
"loss": 0.0212,
|
| 1637 |
+
"step": 118500
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 23.82,
|
| 1641 |
+
"learning_rate": 5.236188951160928e-05,
|
| 1642 |
+
"loss": 0.0227,
|
| 1643 |
+
"step": 119000
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 23.92,
|
| 1647 |
+
"learning_rate": 5.216172938350681e-05,
|
| 1648 |
+
"loss": 0.0188,
|
| 1649 |
+
"step": 119500
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 24.0,
|
| 1653 |
+
"eval_loss": 0.362006276845932,
|
| 1654 |
+
"eval_lowercase_match_acc": 93.1466,
|
| 1655 |
+
"eval_runtime": 4253.911,
|
| 1656 |
+
"eval_samples_per_second": 5.203,
|
| 1657 |
+
"eval_steps_per_second": 2.602,
|
| 1658 |
+
"step": 119904
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 24.02,
|
| 1662 |
+
"learning_rate": 5.196156925540433e-05,
|
| 1663 |
+
"loss": 0.0202,
|
| 1664 |
+
"step": 120000
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 24.12,
|
| 1668 |
+
"learning_rate": 5.176140912730184e-05,
|
| 1669 |
+
"loss": 0.0173,
|
| 1670 |
+
"step": 120500
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 24.22,
|
| 1674 |
+
"learning_rate": 5.156124899919936e-05,
|
| 1675 |
+
"loss": 0.0188,
|
| 1676 |
+
"step": 121000
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 24.32,
|
| 1680 |
+
"learning_rate": 5.136108887109689e-05,
|
| 1681 |
+
"loss": 0.0171,
|
| 1682 |
+
"step": 121500
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 24.42,
|
| 1686 |
+
"learning_rate": 5.1160928742994394e-05,
|
| 1687 |
+
"loss": 0.0202,
|
| 1688 |
+
"step": 122000
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 24.52,
|
| 1692 |
+
"learning_rate": 5.096076861489192e-05,
|
| 1693 |
+
"loss": 0.0191,
|
| 1694 |
+
"step": 122500
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 24.62,
|
| 1698 |
+
"learning_rate": 5.0760608486789427e-05,
|
| 1699 |
+
"loss": 0.0189,
|
| 1700 |
+
"step": 123000
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 24.72,
|
| 1704 |
+
"learning_rate": 5.056044835868695e-05,
|
| 1705 |
+
"loss": 0.0212,
|
| 1706 |
+
"step": 123500
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 24.82,
|
| 1710 |
+
"learning_rate": 5.036028823058447e-05,
|
| 1711 |
+
"loss": 0.0183,
|
| 1712 |
+
"step": 124000
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 24.92,
|
| 1716 |
+
"learning_rate": 5.0160128102481985e-05,
|
| 1717 |
+
"loss": 0.0179,
|
| 1718 |
+
"step": 124500
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 25.0,
|
| 1722 |
+
"eval_loss": 0.3684503436088562,
|
| 1723 |
+
"eval_lowercase_match_acc": 93.1692,
|
| 1724 |
+
"eval_runtime": 4597.5953,
|
| 1725 |
+
"eval_samples_per_second": 4.814,
|
| 1726 |
+
"eval_steps_per_second": 2.407,
|
| 1727 |
+
"step": 124900
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 25.02,
|
| 1731 |
+
"learning_rate": 4.9959967974379505e-05,
|
| 1732 |
+
"loss": 0.0189,
|
| 1733 |
+
"step": 125000
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 25.12,
|
| 1737 |
+
"learning_rate": 4.9759807846277025e-05,
|
| 1738 |
+
"loss": 0.016,
|
| 1739 |
+
"step": 125500
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 25.22,
|
| 1743 |
+
"learning_rate": 4.955964771817454e-05,
|
| 1744 |
+
"loss": 0.0162,
|
| 1745 |
+
"step": 126000
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 25.32,
|
| 1749 |
+
"learning_rate": 4.9359487590072064e-05,
|
| 1750 |
+
"loss": 0.0162,
|
| 1751 |
+
"step": 126500
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 25.42,
|
| 1755 |
+
"learning_rate": 4.9159327461969577e-05,
|
| 1756 |
+
"loss": 0.0151,
|
| 1757 |
+
"step": 127000
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 25.52,
|
| 1761 |
+
"learning_rate": 4.8959167333867096e-05,
|
| 1762 |
+
"loss": 0.0165,
|
| 1763 |
+
"step": 127500
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 25.62,
|
| 1767 |
+
"learning_rate": 4.875900720576461e-05,
|
| 1768 |
+
"loss": 0.0181,
|
| 1769 |
+
"step": 128000
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 25.72,
|
| 1773 |
+
"learning_rate": 4.8558847077662135e-05,
|
| 1774 |
+
"loss": 0.0152,
|
| 1775 |
+
"step": 128500
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 25.82,
|
| 1779 |
+
"learning_rate": 4.835868694955965e-05,
|
| 1780 |
+
"loss": 0.019,
|
| 1781 |
+
"step": 129000
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 25.92,
|
| 1785 |
+
"learning_rate": 4.815852682145717e-05,
|
| 1786 |
+
"loss": 0.021,
|
| 1787 |
+
"step": 129500
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 26.0,
|
| 1791 |
+
"eval_loss": 0.3595723509788513,
|
| 1792 |
+
"eval_lowercase_match_acc": 93.2279,
|
| 1793 |
+
"eval_runtime": 5924.6722,
|
| 1794 |
+
"eval_samples_per_second": 3.736,
|
| 1795 |
+
"eval_steps_per_second": 1.868,
|
| 1796 |
+
"step": 129896
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 26.02,
|
| 1800 |
+
"learning_rate": 4.795836669335468e-05,
|
| 1801 |
+
"loss": 0.0191,
|
| 1802 |
+
"step": 130000
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 26.12,
|
| 1806 |
+
"learning_rate": 4.775820656525221e-05,
|
| 1807 |
+
"loss": 0.0131,
|
| 1808 |
+
"step": 130500
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 26.22,
|
| 1812 |
+
"learning_rate": 4.755804643714972e-05,
|
| 1813 |
+
"loss": 0.0156,
|
| 1814 |
+
"step": 131000
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 26.32,
|
| 1818 |
+
"learning_rate": 4.735788630904724e-05,
|
| 1819 |
+
"loss": 0.0154,
|
| 1820 |
+
"step": 131500
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 26.42,
|
| 1824 |
+
"learning_rate": 4.715772618094476e-05,
|
| 1825 |
+
"loss": 0.0155,
|
| 1826 |
+
"step": 132000
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 26.52,
|
| 1830 |
+
"learning_rate": 4.695756605284228e-05,
|
| 1831 |
+
"loss": 0.0156,
|
| 1832 |
+
"step": 132500
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 26.62,
|
| 1836 |
+
"learning_rate": 4.675740592473979e-05,
|
| 1837 |
+
"loss": 0.0153,
|
| 1838 |
+
"step": 133000
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 26.72,
|
| 1842 |
+
"learning_rate": 4.655724579663731e-05,
|
| 1843 |
+
"loss": 0.016,
|
| 1844 |
+
"step": 133500
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 26.82,
|
| 1848 |
+
"learning_rate": 4.635708566853483e-05,
|
| 1849 |
+
"loss": 0.0172,
|
| 1850 |
+
"step": 134000
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 26.92,
|
| 1854 |
+
"learning_rate": 4.615692554043235e-05,
|
| 1855 |
+
"loss": 0.0165,
|
| 1856 |
+
"step": 134500
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 27.0,
|
| 1860 |
+
"eval_loss": 0.3980076014995575,
|
| 1861 |
+
"eval_lowercase_match_acc": 93.1873,
|
| 1862 |
+
"eval_runtime": 4539.563,
|
| 1863 |
+
"eval_samples_per_second": 4.876,
|
| 1864 |
+
"eval_steps_per_second": 2.438,
|
| 1865 |
+
"step": 134892
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 27.02,
|
| 1869 |
+
"learning_rate": 4.595676541232986e-05,
|
| 1870 |
+
"loss": 0.0168,
|
| 1871 |
+
"step": 135000
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 27.12,
|
| 1875 |
+
"learning_rate": 4.575660528422738e-05,
|
| 1876 |
+
"loss": 0.0139,
|
| 1877 |
+
"step": 135500
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 27.22,
|
| 1881 |
+
"learning_rate": 4.55564451561249e-05,
|
| 1882 |
+
"loss": 0.0136,
|
| 1883 |
+
"step": 136000
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 27.32,
|
| 1887 |
+
"learning_rate": 4.535628502802242e-05,
|
| 1888 |
+
"loss": 0.0146,
|
| 1889 |
+
"step": 136500
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 27.42,
|
| 1893 |
+
"learning_rate": 4.515612489991994e-05,
|
| 1894 |
+
"loss": 0.0143,
|
| 1895 |
+
"step": 137000
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 27.52,
|
| 1899 |
+
"learning_rate": 4.4955964771817454e-05,
|
| 1900 |
+
"loss": 0.0173,
|
| 1901 |
+
"step": 137500
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 27.62,
|
| 1905 |
+
"learning_rate": 4.4755804643714974e-05,
|
| 1906 |
+
"loss": 0.0148,
|
| 1907 |
+
"step": 138000
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 27.72,
|
| 1911 |
+
"learning_rate": 4.4555644515612493e-05,
|
| 1912 |
+
"loss": 0.0143,
|
| 1913 |
+
"step": 138500
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 27.82,
|
| 1917 |
+
"learning_rate": 4.435548438751001e-05,
|
| 1918 |
+
"loss": 0.0149,
|
| 1919 |
+
"step": 139000
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 27.92,
|
| 1923 |
+
"learning_rate": 4.4155324259407526e-05,
|
| 1924 |
+
"loss": 0.0147,
|
| 1925 |
+
"step": 139500
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 28.0,
|
| 1929 |
+
"eval_loss": 0.4007766544818878,
|
| 1930 |
+
"eval_lowercase_match_acc": 93.0608,
|
| 1931 |
+
"eval_runtime": 5405.4624,
|
| 1932 |
+
"eval_samples_per_second": 4.095,
|
| 1933 |
+
"eval_steps_per_second": 2.048,
|
| 1934 |
+
"step": 139888
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 28.02,
|
| 1938 |
+
"learning_rate": 4.3955164131305046e-05,
|
| 1939 |
+
"loss": 0.0096,
|
| 1940 |
+
"step": 140000
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 28.12,
|
| 1944 |
+
"learning_rate": 4.3755004003202565e-05,
|
| 1945 |
+
"loss": 0.0118,
|
| 1946 |
+
"step": 140500
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 28.22,
|
| 1950 |
+
"learning_rate": 4.3554843875100085e-05,
|
| 1951 |
+
"loss": 0.0134,
|
| 1952 |
+
"step": 141000
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 28.32,
|
| 1956 |
+
"learning_rate": 4.33546837469976e-05,
|
| 1957 |
+
"loss": 0.0145,
|
| 1958 |
+
"step": 141500
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 28.42,
|
| 1962 |
+
"learning_rate": 4.3154523618895124e-05,
|
| 1963 |
+
"loss": 0.0112,
|
| 1964 |
+
"step": 142000
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 28.52,
|
| 1968 |
+
"learning_rate": 4.295436349079264e-05,
|
| 1969 |
+
"loss": 0.0165,
|
| 1970 |
+
"step": 142500
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 28.62,
|
| 1974 |
+
"learning_rate": 4.2754203362690156e-05,
|
| 1975 |
+
"loss": 0.0151,
|
| 1976 |
+
"step": 143000
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 28.72,
|
| 1980 |
+
"learning_rate": 4.255404323458767e-05,
|
| 1981 |
+
"loss": 0.0155,
|
| 1982 |
+
"step": 143500
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 28.82,
|
| 1986 |
+
"learning_rate": 4.2353883106485196e-05,
|
| 1987 |
+
"loss": 0.0162,
|
| 1988 |
+
"step": 144000
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 28.92,
|
| 1992 |
+
"learning_rate": 4.215372297838271e-05,
|
| 1993 |
+
"loss": 0.0149,
|
| 1994 |
+
"step": 144500
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 29.0,
|
| 1998 |
+
"eval_loss": 0.4174624979496002,
|
| 1999 |
+
"eval_lowercase_match_acc": 93.0337,
|
| 2000 |
+
"eval_runtime": 3557.364,
|
| 2001 |
+
"eval_samples_per_second": 6.222,
|
| 2002 |
+
"eval_steps_per_second": 3.111,
|
| 2003 |
+
"step": 144884
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 29.02,
|
| 2007 |
+
"learning_rate": 4.195356285028023e-05,
|
| 2008 |
+
"loss": 0.0132,
|
| 2009 |
+
"step": 145000
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 29.12,
|
| 2013 |
+
"learning_rate": 4.175340272217774e-05,
|
| 2014 |
+
"loss": 0.0158,
|
| 2015 |
+
"step": 145500
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 29.22,
|
| 2019 |
+
"learning_rate": 4.155324259407527e-05,
|
| 2020 |
+
"loss": 0.0111,
|
| 2021 |
+
"step": 146000
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"epoch": 29.32,
|
| 2025 |
+
"learning_rate": 4.135308246597278e-05,
|
| 2026 |
+
"loss": 0.0118,
|
| 2027 |
+
"step": 146500
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 29.42,
|
| 2031 |
+
"learning_rate": 4.11529223378703e-05,
|
| 2032 |
+
"loss": 0.0122,
|
| 2033 |
+
"step": 147000
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 29.52,
|
| 2037 |
+
"learning_rate": 4.095276220976781e-05,
|
| 2038 |
+
"loss": 0.011,
|
| 2039 |
+
"step": 147500
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 29.62,
|
| 2043 |
+
"learning_rate": 4.075260208166534e-05,
|
| 2044 |
+
"loss": 0.0148,
|
| 2045 |
+
"step": 148000
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 29.72,
|
| 2049 |
+
"learning_rate": 4.055244195356285e-05,
|
| 2050 |
+
"loss": 0.0129,
|
| 2051 |
+
"step": 148500
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 29.82,
|
| 2055 |
+
"learning_rate": 4.035228182546037e-05,
|
| 2056 |
+
"loss": 0.0142,
|
| 2057 |
+
"step": 149000
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 29.92,
|
| 2061 |
+
"learning_rate": 4.0152121697357884e-05,
|
| 2062 |
+
"loss": 0.0126,
|
| 2063 |
+
"step": 149500
|
| 2064 |
+
},
|
| 2065 |
+
{
|
| 2066 |
+
"epoch": 30.0,
|
| 2067 |
+
"eval_loss": 0.4186698794364929,
|
| 2068 |
+
"eval_lowercase_match_acc": 93.1963,
|
| 2069 |
+
"eval_runtime": 3676.3282,
|
| 2070 |
+
"eval_samples_per_second": 6.021,
|
| 2071 |
+
"eval_steps_per_second": 3.011,
|
| 2072 |
+
"step": 149880
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 30.02,
|
| 2076 |
+
"learning_rate": 3.995196156925541e-05,
|
| 2077 |
+
"loss": 0.0141,
|
| 2078 |
+
"step": 150000
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 30.12,
|
| 2082 |
+
"learning_rate": 3.975180144115292e-05,
|
| 2083 |
+
"loss": 0.0103,
|
| 2084 |
+
"step": 150500
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 30.22,
|
| 2088 |
+
"learning_rate": 3.955164131305044e-05,
|
| 2089 |
+
"loss": 0.0131,
|
| 2090 |
+
"step": 151000
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 30.32,
|
| 2094 |
+
"learning_rate": 3.9351481184947956e-05,
|
| 2095 |
+
"loss": 0.0108,
|
| 2096 |
+
"step": 151500
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 30.42,
|
| 2100 |
+
"learning_rate": 3.915132105684548e-05,
|
| 2101 |
+
"loss": 0.0093,
|
| 2102 |
+
"step": 152000
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 30.52,
|
| 2106 |
+
"learning_rate": 3.8951160928742995e-05,
|
| 2107 |
+
"loss": 0.0132,
|
| 2108 |
+
"step": 152500
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 30.62,
|
| 2112 |
+
"learning_rate": 3.8751000800640514e-05,
|
| 2113 |
+
"loss": 0.0123,
|
| 2114 |
+
"step": 153000
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 30.72,
|
| 2118 |
+
"learning_rate": 3.855084067253803e-05,
|
| 2119 |
+
"loss": 0.0126,
|
| 2120 |
+
"step": 153500
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 30.82,
|
| 2124 |
+
"learning_rate": 3.8350680544435554e-05,
|
| 2125 |
+
"loss": 0.0097,
|
| 2126 |
+
"step": 154000
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 30.92,
|
| 2130 |
+
"learning_rate": 3.8150520416333066e-05,
|
| 2131 |
+
"loss": 0.0139,
|
| 2132 |
+
"step": 154500
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 31.0,
|
| 2136 |
+
"eval_loss": 0.4269045889377594,
|
| 2137 |
+
"eval_lowercase_match_acc": 93.0788,
|
| 2138 |
+
"eval_runtime": 3725.6857,
|
| 2139 |
+
"eval_samples_per_second": 5.941,
|
| 2140 |
+
"eval_steps_per_second": 2.971,
|
| 2141 |
+
"step": 154876
|
| 2142 |
+
},
|
| 2143 |
+
{
|
| 2144 |
+
"epoch": 31.02,
|
| 2145 |
+
"learning_rate": 3.7950360288230586e-05,
|
| 2146 |
+
"loss": 0.0139,
|
| 2147 |
+
"step": 155000
|
| 2148 |
+
},
|
| 2149 |
+
{
|
| 2150 |
+
"epoch": 31.12,
|
| 2151 |
+
"learning_rate": 3.77502001601281e-05,
|
| 2152 |
+
"loss": 0.0113,
|
| 2153 |
+
"step": 155500
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 31.22,
|
| 2157 |
+
"learning_rate": 3.7550040032025625e-05,
|
| 2158 |
+
"loss": 0.0108,
|
| 2159 |
+
"step": 156000
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 31.33,
|
| 2163 |
+
"learning_rate": 3.734987990392314e-05,
|
| 2164 |
+
"loss": 0.0105,
|
| 2165 |
+
"step": 156500
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 31.43,
|
| 2169 |
+
"learning_rate": 3.714971977582066e-05,
|
| 2170 |
+
"loss": 0.012,
|
| 2171 |
+
"step": 157000
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 31.53,
|
| 2175 |
+
"learning_rate": 3.694955964771817e-05,
|
| 2176 |
+
"loss": 0.0119,
|
| 2177 |
+
"step": 157500
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 31.63,
|
| 2181 |
+
"learning_rate": 3.67493995196157e-05,
|
| 2182 |
+
"loss": 0.0109,
|
| 2183 |
+
"step": 158000
|
| 2184 |
+
},
|
| 2185 |
+
{
|
| 2186 |
+
"epoch": 31.73,
|
| 2187 |
+
"learning_rate": 3.654923939151321e-05,
|
| 2188 |
+
"loss": 0.0131,
|
| 2189 |
+
"step": 158500
|
| 2190 |
+
},
|
| 2191 |
+
{
|
| 2192 |
+
"epoch": 31.83,
|
| 2193 |
+
"learning_rate": 3.634907926341073e-05,
|
| 2194 |
+
"loss": 0.011,
|
| 2195 |
+
"step": 159000
|
| 2196 |
+
},
|
| 2197 |
+
{
|
| 2198 |
+
"epoch": 31.93,
|
| 2199 |
+
"learning_rate": 3.614891913530825e-05,
|
| 2200 |
+
"loss": 0.0111,
|
| 2201 |
+
"step": 159500
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 32.0,
|
| 2205 |
+
"eval_loss": 0.43798354268074036,
|
| 2206 |
+
"eval_lowercase_match_acc": 93.1466,
|
| 2207 |
+
"eval_runtime": 3803.2601,
|
| 2208 |
+
"eval_samples_per_second": 5.82,
|
| 2209 |
+
"eval_steps_per_second": 2.91,
|
| 2210 |
+
"step": 159872
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 32.03,
|
| 2214 |
+
"learning_rate": 3.594875900720577e-05,
|
| 2215 |
+
"loss": 0.0108,
|
| 2216 |
+
"step": 160000
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 32.13,
|
| 2220 |
+
"learning_rate": 3.574859887910328e-05,
|
| 2221 |
+
"loss": 0.0092,
|
| 2222 |
+
"step": 160500
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 32.23,
|
| 2226 |
+
"learning_rate": 3.55484387510008e-05,
|
| 2227 |
+
"loss": 0.0117,
|
| 2228 |
+
"step": 161000
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 32.33,
|
| 2232 |
+
"learning_rate": 3.534827862289832e-05,
|
| 2233 |
+
"loss": 0.0103,
|
| 2234 |
+
"step": 161500
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 32.43,
|
| 2238 |
+
"learning_rate": 3.514811849479584e-05,
|
| 2239 |
+
"loss": 0.0105,
|
| 2240 |
+
"step": 162000
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 32.53,
|
| 2244 |
+
"learning_rate": 3.494795836669335e-05,
|
| 2245 |
+
"loss": 0.0114,
|
| 2246 |
+
"step": 162500
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 32.63,
|
| 2250 |
+
"learning_rate": 3.474779823859087e-05,
|
| 2251 |
+
"loss": 0.0116,
|
| 2252 |
+
"step": 163000
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 32.73,
|
| 2256 |
+
"learning_rate": 3.454763811048839e-05,
|
| 2257 |
+
"loss": 0.0103,
|
| 2258 |
+
"step": 163500
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 32.83,
|
| 2262 |
+
"learning_rate": 3.434747798238591e-05,
|
| 2263 |
+
"loss": 0.0108,
|
| 2264 |
+
"step": 164000
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 32.93,
|
| 2268 |
+
"learning_rate": 3.414731785428343e-05,
|
| 2269 |
+
"loss": 0.0108,
|
| 2270 |
+
"step": 164500
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 33.0,
|
| 2274 |
+
"eval_loss": 0.4487093687057495,
|
| 2275 |
+
"eval_lowercase_match_acc": 93.2776,
|
| 2276 |
+
"eval_runtime": 3787.9684,
|
| 2277 |
+
"eval_samples_per_second": 5.844,
|
| 2278 |
+
"eval_steps_per_second": 2.922,
|
| 2279 |
+
"step": 164868
|
| 2280 |
+
}
|
| 2281 |
+
],
|
| 2282 |
+
"max_steps": 249800,
|
| 2283 |
+
"num_train_epochs": 50,
|
| 2284 |
+
"total_flos": 6.948168358888673e+17,
|
| 2285 |
+
"trial_name": null,
|
| 2286 |
+
"trial_params": null
|
| 2287 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f2e0653dac72edc1bb1b56a4aa9a930956cfb32f45dbdce16523c2a6444ef60
|
| 3 |
+
size 3579
|